scom-org colab

#install.packages(c('tidyverse','lme4'))
if (T) {
# load packages
library("tidyverse")
#library("quarto")
library("lme4")
# clear workspace
rm(list=ls())
}

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.0     ✔ readr     2.1.4
✔ forcats   1.0.0     ✔ stringr   1.5.0
✔ ggplot2   3.4.1     ✔ tibble    3.1.8
✔ lubridate 1.9.2     ✔ tidyr     1.3.0
✔ purrr     1.0.1     
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
Loading required package: Matrix


Attaching package: 'Matrix'


The following objects are masked from 'package:tidyr':

    expand, pack, unpack

# working directory
if (!grepl("/qmd", getwd(), fixed=T)) {setwd("qmd/")}; getwd();

[1] "/home/sol-nhl/rnd/r/projects/scom-org/qmd"

# load functions
vals_normalize <- function(x,y) {return (data.frame(id=x, nv=(y - min(y)) / (max(y) - min(y))))}
# load fb post dataset
fn = "https://raw.githubusercontent.com/nils-holmberg/scom-org/main/csv/fb-sa-230314.csv"
fn = "../csv/fb-sa-230314.csv"
dtp = read.table(fn, sep='\t', header=T, strip.white=TRUE, stringsAsFactors=FALSE)
dtp = dtp |> as_tibble() |> mutate(month=month-30)

#
dtp |> names()

 [1] "id"         "text"       "org"        "time"       "lang"      
 [6] "follow"     "e_lc"       "e_cc"       "e_sc"       "e_rc"      
[11] "e_index"    "emoji"      "emnum"      "sa_val"     "sa_pos"    
[16] "sa_neg"     "sa_frq"     "group"      "date"       "bins"      
[21] "index"      "month"      "sa_int_abs" "sa_int"     "wc"        
[26] "out"        "org_type"  

240119: table descriptives

tmp = dtp |> 
  select(c(19,22,3,27,14,23,25,11,6)) |>
  mutate(date=as.Date(date)) |>
  mutate(date=format(date, "%Y-%m")) |>
  mutate(
    m1_sa_val=sa_val,
    m2_sa_int_abs=sa_int_abs,
    m3_wc=wc,
    m4_sa_int_rel=sa_int_abs / wc,
    m5_e_index=e_index,
    m6_follow=follow,
    m7_date=date
  )
#write.table(tmp, "/tmp/scom/fb-sa-240119.tsv", sep="\t", quot=T, row.names=F)

• select columns
• sample 1000 rows
• summarize chatgpt
• min(time), max(time)
• plot gantt diagram
• mean(measures)
• sd(measures)
• by org, org_type

aggregate measures by org

# Aggregate the data
aggregated_data <- tmp %>%
  select(starts_with("m1_"), starts_with("m2_"), starts_with("m3_"),
         starts_with("m4_"), starts_with("m5_"), starts_with("m6_"),
         starts_with("m7_"), org) %>%
  group_by(org) %>%
  summarize(across(starts_with("m1_"):starts_with("m6_"),
                   list(mean = ~ mean(., na.rm = TRUE),
                        sd = ~ sd(., na.rm = TRUE))),
            m7_first = first(m7_date),
            m7_last = last(m7_date))

# View the aggregated data
result_df = aggregated_data |> as_tibble()
cat(simplermarkdown::md_table(result_df))

org	m1_sa_val_mean	m1_sa_val_sd	m2_sa_int_abs_mean	m2_sa_int_abs_sd	m3_wc_mean	m3_wc_sd	m4_sa_int_rel_mean	m4_sa_int_rel_sd	m5_e_index_mean	m5_e_index_sd	m6_follow_mean	m6_follow_sd	m7_first	m7_last
AMREFNordic	1.98657718	4.529165	4.818792	5.474824	52.38255	43.15694	0.09991600	0.20211051	35.11409	148.344674	1057.9329	67.85723	2016-02	2020-10
ActionAidSweden	0.74117647	5.549409	7.700000	6.833901	74.91029	48.63348	0.10211565	0.10239044	61.69412	215.264233	13759.1471	1420.06370	2015-11	2020-10
Afghanistankommitten	1.96440489	4.551470	4.820912	5.051425	49.81090	35.02964	0.10132240	0.15742427	126.69744	249.499329	14307.7286	4328.88580	2015-11	2020-10
Afrikagrupperna	1.10839161	4.368805	4.541958	5.423470	63.38811	54.47465	0.06589123	0.06224883	60.31119	107.691491	10479.9301	779.78744	2018-10	2020-10
Alzheimerfonden	1.75196850	4.455921	5.082677	4.862238	51.25591	33.33851	0.10099255	0.08452541	236.77559	187.560627	8829.9213	341.91440	2017-11	2020-10
AmnestySverige	-1.63542739	5.158212	6.317199	5.535295	56.03090	41.98683	0.11555812	0.08959921	618.28012	864.433613	93597.2049	5602.06850	2015-11	2020-10
AnhorigasRiksforbund	1.45377258	4.411932	3.572795	9.117336	45.79171	100.45138	0.07489957	0.15698286	50.93199	67.994162	1731.2338	749.10248	2016-02	2020-10
BRIS	1.98502674	4.361820	4.896257	4.982081	58.14973	39.92223	0.07803907	0.08388972	246.89198	623.556126	86262.0075	5668.68984	2015-11	2020-10
Barnfonden	3.29914530	4.630835	5.746032	4.573119	58.51770	31.59881	0.10538129	0.09007651	122.27839	545.049865	27980.2991	588.51996	2015-11	2020-10
BirdLifeSverige	2.51184346	4.849552	3.467559	5.686276	42.41607	62.56302	0.08623228	0.14175573	159.02163	236.711845	13579.8620	2208.42402	2015-11	2020-10
Blomsterfonden	1.45754717	2.724836	1.910377	3.096625	16.44811	14.47116	0.11053328	0.21173754	33.75943	36.942041	1346.5236	46.21149	2017-11	2020-10
ClownerutanGranser	6.22085890	6.358883	11.716039	7.916893	96.66871	57.23720	0.13201667	0.08706294	151.87730	171.956025	13600.5092	2235.24978	2015-11	2020-10
Diabetesfonden	2.66153846	3.878131	3.646154	4.299094	35.81538	28.00664	0.08307258	0.08073476	154.41538	353.218899	6380.9692	80.08218	2018-10	2020-10
EcpatSverige	1.24109015	4.891099	6.641509	5.139585	72.98742	37.54459	0.09211587	0.07521224	410.32075	510.957661	30949.9434	4173.20668	2015-11	2020-10
Erikshjalpen	2.21105072	3.979301	4.613225	5.565064	55.90308	40.19337	0.07448751	0.07186158	59.92391	83.858273	11736.1603	1525.85654	2015-11	2020-10
FNforbundet	1.45697329	3.606496	3.658754	3.855467	39.95153	32.28942	0.08639258	0.08284888	73.66766	198.558514	13871.8853	2362.45010	2015-11	2020-10
FairtradeSverige	2.81760204	3.730533	4.414541	3.801975	62.72449	36.19414	0.07692614	0.07223328	200.60714	360.358005	111179.0587	1258.10613	2015-11	2020-10
FreezonenKvinnoTjejochBrottsofferjour	-0.54583333	6.066402	5.995833	8.613261	59.45000	73.28369	0.08884198	0.10993876	15.76250	32.112737	724.8083	143.91166	2019-02	2020-10
Friluftsframjandet	5.91886410	5.147174	7.452333	5.513865	60.36511	39.25625	0.13903490	0.10284313	173.18458	454.247990	33490.0142	6286.52096	2018-05	2020-10
GbgStadsmission	4.16451149	6.024234	6.171695	7.604624	69.03161	68.87829	0.08982145	0.09545385	111.34698	274.448215	9628.6149	1534.02388	2015-11	2020-10
HRFriks	2.06995582	4.232063	4.909426	4.648584	58.50810	33.16577	0.08253229	0.07706519	67.40795	65.380627	3316.6642	726.28098	2015-11	2020-10
HRWSweden	-1.42503439	4.645514	5.881706	5.692030	56.65337	42.59898	0.11116072	0.10311194	5.52132	8.359305	1148.7153	526.29005	2017-09	2020-10
Hjartebarnsfonden	4.75474255	6.219701	9.134146	8.001842	98.22358	70.58165	0.09587636	0.07960570	165.55962	215.632753	7657.9119	443.22598	2018-10	2020-10
IslamicReliefSverige	2.88640840	5.540874	7.523309	6.815087	70.61129	59.84115	0.11256628	0.08983337	71.57058	186.052267	14959.8181	2750.99736	2015-11	2020-10
Lakarmissionen	3.52380952	5.087760	7.142857	8.167881	65.30736	73.19246	0.11334375	0.10656306	301.31169	831.363598	26709.8052	230.51976	2017-11	2020-10
Latinamerikagrupperna	0.45562130	4.352009	4.254438	6.234533	46.61538	48.25157	0.11617375	0.21796089	25.36095	25.940521	6663.1361	20.00444	2020-01	2020-10
Laxhjalpen	4.57183908	4.976840	5.623563	5.607212	52.03448	39.66310	0.13232989	0.19188281	20.24856	16.895191	2153.8405	346.66695	2015-11	2020-10
MPSweden	2.49685535	5.013746	6.081761	5.263883	85.33333	50.02527	0.07911091	0.06478618	2000.22013	3142.275533	630712.9371	35602.01724	2015-11	2020-10
Mattecentrum	3.51657941	3.907242	4.045375	4.044041	28.45986	27.18002	0.20837502	0.57221327	59.45288	89.755719	25031.7033	2281.47222	2016-01	2020-10
Njurfonden	2.67701863	5.607587	4.701863	5.659996	50.26708	38.55901	0.07343755	0.07906510	131.02484	270.474397	1055.8075	273.74170	2017-11	2020-10
Nordensark	3.15860735	4.211693	4.837524	4.732445	64.71373	47.76752	0.08228628	0.08914184	239.68085	273.435062	19762.6692	828.67588	2019-05	2020-10
PMUfb	2.30000000	4.389165	5.502532	5.730701	54.14684	47.08514	0.11275814	0.14077204	105.31772	192.080350	5628.1076	1228.15642	2015-11	2020-10
PlanSverige	1.04647160	5.623524	7.509466	6.827794	78.65491	57.07897	0.10060339	0.08313444	653.44148	1120.796084	57794.6136	8784.30106	2015-11	2020-10
Psoriasisforbundet	2.58348624	3.805581	3.977982	4.479474	57.89541	36.05330	0.06908573	0.08226927	58.15413	48.845891	5470.0972	299.81309	2017-11	2020-10
RaoulWallenbergAcademy	2.85009488	5.267585	5.981025	6.235525	75.65655	62.13528	0.07483660	0.06711849	98.38710	188.978488	7810.8027	843.09015	2018-08	2020-10
Reumatikerforbundet	1.34036939	3.763389	3.656992	4.449465	38.40633	33.97568	0.08073637	0.10330273	99.83465	96.404869	10907.2260	633.66903	2017-11	2020-10
RiksforbundetHjartLung	2.57180851	4.242346	4.728723	4.934546	61.44947	46.42804	0.07982456	0.08555846	113.08910	142.409562	6618.4362	4822.72468	2015-11	2020-10
SLMK.1981	1.02400835	3.485520	4.255741	4.159357	56.31106	37.49351	0.07506007	0.06762310	44.63361	55.199992	1819.9843	252.87087	2015-11	2020-10
Sportfiskarna	2.51242236	4.153902	3.940994	4.284907	44.07298	34.44471	0.10443204	0.13385953	151.07764	403.589285	14315.1724	3182.79437	2016-01	2020-10
StiftelsenFriends	0.51911221	5.073589	6.889026	9.907723	59.39088	78.49812	0.12106890	0.14105022	712.42910	4860.725551	72514.4168	7689.76317	2015-11	2020-10
TeachForSweden	3.83546326	4.805006	4.822684	5.259250	64.57987	49.65543	0.07461921	0.08291682	21.98722	18.075216	3180.6262	896.52890	2016-02	2020-10
Teskedsorden	1.40559441	6.380054	8.097902	6.847527	95.84965	62.53079	0.08598969	0.06990109	53.90909	57.993092	5120.2552	293.80251	2019-01	2020-10
Tjejzonen	4.54389313	6.842393	9.799618	8.213681	89.66412	59.05290	0.12228492	0.16231479	66.71947	114.499190	5156.9828	984.37492	2016-01	2020-10
UNICEF-Sverige	1.69633508	5.177756	6.203141	4.791742	51.69319	25.20222	0.12654664	0.10933415	1111.96859	3250.357429	306713.8963	12509.40429	2015-11	2020-10
WikimediaSverige	2.93508772	4.577894	3.970175	5.156001	55.56667	49.59339	0.07170849	0.09305698	34.01404	108.908677	2824.3421	1803.24839	2015-11	2020-10
WorldAnimalProtectionSverige	0.96117274	4.510372	5.523772	4.766456	49.13946	29.00542	0.11939871	0.10489676	1018.28051	1334.483399	85681.2448	10013.07218	2015-11	2020-10
actsvenskakyrkan	1.77307692	3.935775	4.863462	4.338494	44.84327	30.02276	0.11417106	0.10073909	245.88654	428.189166	19163.4048	5192.57421	2015-11	2020-10
astmaallergiforbundet	1.46388606	3.433759	3.138352	3.703247	40.04578	29.25603	0.07971094	0.09239395	93.15158	112.295546	11449.0610	3129.46554	2015-11	2020-10
autismaspergersverige	1.63447433	3.690556	3.996333	3.974981	65.41687	34.52161	0.06477703	0.08565146	276.36308	284.710928	23747.9804	3208.57887	2017-03	2020-10
barncancerfonden	2.71072664	4.460281	6.033910	4.694499	66.16817	32.42958	0.09312299	0.07305899	607.29343	636.998838	111042.3744	19777.15616	2015-11	2020-10
barndiabetesfonden	7.44754316	8.121434	8.974768	8.838874	68.23904	55.37763	0.12133282	0.11737756	254.80876	506.392375	12882.9442	3926.03635	2015-11	2020-10
barnrattsbyransverige	3.29430380	5.604315	7.161392	7.637162	77.40506	68.82345	0.10234088	0.08659004	77.61709	61.059967	2815.8291	532.32249	2015-11	2020-10
berattarministeriet	3.26931818	4.654768	4.480682	5.470333	48.66818	42.93103	0.09299559	0.09880561	47.85341	55.127220	5640.2875	1164.35966	2015-11	2020-10
brostcancerforbundet	2.49945115	4.628359	5.711306	8.284042	51.71570	69.85218	0.14058239	0.21443005	180.70033	253.225633	4875.5071	1654.56312	2016-02	2020-10
cancerfonden	1.98955614	3.790906	4.680592	4.127938	40.42037	23.77020	0.12459840	0.12057903	1427.48999	3254.472204	152398.9896	11865.91478	2015-11	2020-10
celiakiforbundet	0.68571429	2.913966	2.451429	3.777734	44.77714	48.77369	0.05155114	0.08293153	105.47429	142.545577	11783.3371	1591.61788	2015-11	2020-10
childhoodsverige	1.11904762	6.800227	10.658730	7.192498	106.86243	60.79262	0.10863908	0.06822859	454.92063	642.395504	22032.7566	761.26881	2017-11	2020-10
civilrightsdefenders	1.11095506	7.037596	10.841292	8.359458	62.07163	30.92733	0.17092530	0.10963457	103.80758	484.434248	41217.3076	10022.13623	2015-11	2020-10
diakonia.se	1.53232759	3.739208	4.497845	4.168171	45.28233	32.82824	0.10585067	0.09334381	116.19828	267.921307	21924.2177	826.32177	2017-11	2020-10
djurskyddet	1.74518686	4.394604	4.519819	5.083922	54.80294	33.60673	0.08309916	0.08558714	251.46772	409.120679	27072.2695	1693.26288	2015-11	2020-10
emmausstockholm	1.60123330	4.280216	4.176773	4.616975	54.83556	36.64772	0.06964650	0.06854723	31.27955	65.832138	3223.2590	491.96121	2015-11	2020-10
eskilstunastadsmission	3.60444444	4.317982	4.822222	5.455178	43.38000	48.95892	0.15042883	0.28056749	112.51778	128.933836	5198.7422	241.56161	2017-10	2020-10
fondenforpsykiskhalsa	1.36697248	2.923913	2.761468	3.971890	33.43119	34.65822	0.06957677	0.12226562	32.79817	124.784094	1240.7064	194.05384	2016-03	2020-10
foreningenfuruboda	2.02374894	3.579954	2.693808	4.047937	42.62426	37.82015	0.07125921	0.11242269	46.07294	50.838268	2074.0568	636.75539	2015-11	2020-10
forskautandjurforsok	2.12316716	5.742726	5.348974	6.734781	71.81525	70.04871	0.07961377	0.08026455	299.11730	353.172176	67307.8152	2559.70516	2015-11	2020-10
fralsningsarmen	1.50473538	3.286972	3.459053	3.625266	36.04290	23.34208	0.10131023	0.13053100	477.38774	1003.657941	18428.5604	4771.76598	2015-11	2020-10
friskfri	2.23479888	6.479589	8.363891	8.425563	103.61366	69.63653	0.07621839	0.04736977	54.76333	61.042344	5201.3835	1108.06950	2016-05	2020-10
fryshuset	2.74613003	4.494711	5.247678	6.060304	72.51084	54.33805	0.06684365	0.07111194	27.47678	31.729572	11025.6254	297.14463	2019-01	2020-10
hallsverigerent	1.30293160	3.188902	2.713355	3.198580	31.07166	23.32936	0.10178203	0.19820868	292.14821	730.873403	21252.2638	5629.00953	2015-11	2020-10
hela.manniskan	0.98884758	2.785949	1.327138	3.104158	18.01115	28.12614	0.08228724	0.22682523	67.45911	222.335058	1581.1914	805.24357	2015-11	2020-10
hjarnfonden	2.37480190	4.811079	5.956418	6.779792	53.25674	50.56382	0.11555436	0.10831971	351.97544	691.081410	22519.3954	8595.53902	2016-01	2020-10
hjartlungfonden	2.15705521	3.932773	4.628221	4.446840	51.43558	36.07987	0.09951328	0.11282523	138.69202	382.526737	37859.5656	1183.12613	2017-10	2020-10
imsweden.org	1.78327526	4.637606	5.490592	5.264326	63.74216	40.53886	0.08360479	0.07316173	89.79512	234.544910	12939.6376	2517.34222	2016-01	2020-10
iogtnto	0.76242424	3.257075	3.128485	3.595166	39.86424	25.65243	0.07922302	0.09013086	161.99636	210.305917	10521.3588	1318.32744	2016-05	2020-10
kalmarstadsmission	2.42067736	3.709746	3.591800	4.551915	47.38324	47.33442	0.07783630	0.10121708	77.10428	78.033507	3307.8699	1103.26830	2015-11	2020-10
kfumsverige	1.85653409	3.192833	2.907670	3.528586	41.22159	35.87780	0.08222851	0.18383536	18.92614	24.269649	2811.7429	193.61861	2015-11	2020-10
kristnafreds	2.22938776	4.754130	5.930612	5.909385	56.71673	43.74597	0.10486765	0.09471265	25.55837	24.497067	2343.0629	227.32068	2015-11	2020-10
kvinnatillkvinna	0.52587800	5.543852	7.176525	6.167061	63.64048	35.45485	0.11030973	0.08113679	273.14233	1686.407708	41220.6238	6492.71767	2015-11	2020-10
lakareivarlden	0.78558875	4.658372	4.694200	8.237538	60.68190	79.54992	0.06883227	0.08841693	58.61863	98.878235	4760.1670	917.83551	2015-11	2020-10
lakareutangranser	-0.49685535	3.711465	4.004717	4.013546	44.99292	30.28861	0.09158643	0.08405740	779.17846	2533.477871	386301.4434	7224.79893	2015-11	2020-10
lillabarnet	4.11111111	5.209071	4.888889	6.235597	45.43056	55.98435	0.11015768	0.10763638	109.59028	459.368515	2510.2014	202.15758	2015-12	2020-10
linkopingsstadsmission.fb	2.70780856	4.771953	4.658690	5.736770	58.31234	48.63979	0.07622621	0.08996867	50.84383	94.837769	4936.9099	990.48035	2015-11	2020-10
mentorsverige	2.83767228	5.308691	5.202144	7.029443	58.80092	52.02468	0.08576576	0.08306014	48.85605	70.850275	8747.4119	1096.65463	2015-11	2020-10
mindsweden	0.85365854	3.880897	4.567338	4.552533	52.94380	30.93470	0.08469462	0.07272152	232.52492	419.256846	22751.7943	6398.59915	2016-04	2020-10
minstoradag	4.61778846	6.111721	8.992788	7.680907	92.43750	59.79494	0.09927492	0.07977025	1079.75000	2291.102684	86494.5385	9610.87585	2015-12	2020-10
neurosweden	1.54633205	4.223996	4.990347	5.759015	64.84942	55.78829	0.07764060	0.09906922	72.72587	104.134594	15792.7355	308.44860	2018-10	2020-10
nhjalp	1.78260870	3.892177	4.043478	5.635030	47.62609	53.73418	0.07860611	0.07882988	30.28261	70.753543	2333.6087	814.02069	2017-11	2020-10
nonsmokinggeneration	1.49200376	4.006784	4.135466	4.151610	47.88805	32.32075	0.09239962	0.09055191	40.29821	47.730099	5119.7178	290.51878	2015-11	2020-10
operationsmilesverige	4.14052953	5.175474	6.384929	6.569203	70.47454	61.75309	0.11670424	0.14208159	589.69450	805.250381	24605.9888	4568.42982	2015-11	2020-10
organisationen.man	-0.48347613	5.898864	7.658507	8.646497	78.61077	65.98171	0.09111132	0.07958766	149.78213	240.026615	16909.8764	3856.91687	2016-01	2020-10
oxfamsverige	0.07164179	4.849077	6.731343	5.328049	66.94776	38.60523	0.10119904	0.07116472	196.85373	586.009514	13310.0090	2986.41675	2015-11	2020-10
palestinagrupperna	0.61203320	6.288036	5.529046	9.825514	66.95643	96.53871	0.08598682	0.19240083	88.77593	128.497796	7636.9440	543.68663	2015-11	2020-10
parasportSWE	1.54931507	2.428886	1.927397	2.558815	22.22329	16.48954	0.08339481	0.11549583	75.73151	65.827740	4736.6836	613.19622	2016-08	2020-10
prostatacancerforbundetsverige	2.07058824	3.277278	2.870588	3.291690	29.45294	19.46840	0.10474620	0.11974541	197.89412	176.354070	24279.6647	1593.16322	2018-11	2020-10
raddabarnen	0.59744780	5.284399	7.917633	5.884797	75.51392	40.91581	0.10495589	0.06768376	963.22274	2741.992923	156626.8306	17387.09672	2015-11	2020-10
raddningsmissionen	6.52223060	8.722775	11.195931	11.510604	111.76790	85.83747	0.09817405	0.06793927	97.81161	137.024161	12551.5162	1740.08906	2015-11	2020-10
rburiks	1.02370100	2.795556	2.309025	3.548702	33.78487	38.43049	0.06214061	0.08793026	107.00820	136.341647	3544.6600	932.37437	2016-01	2020-10
reachforchangeorg	6.07766990	6.900704	8.550971	8.223035	71.65291	52.04425	0.12640385	0.10659239	16.93932	19.668855	10451.7597	457.85851	2015-11	2020-10
rfsl.forbundet	1.83559457	4.995696	5.181165	6.599925	61.46369	55.34704	0.08665757	0.19962109	141.51317	300.170084	16334.2123	3378.31296	2015-11	2020-10
rfsu.se	1.69082126	5.430000	5.671498	6.449429	62.76006	57.47363	0.09538553	0.16037733	158.40258	950.377736	15730.4815	1576.04155	2017-12	2020-10
rightlivelihood	2.37291280	6.742481	9.575139	10.244566	64.93878	46.69208	0.14286962	0.10582397	43.57885	203.035457	13498.3840	1270.22524	2017-01	2020-10
rodakorset	0.52408931	3.807154	4.723854	3.916797	41.69800	23.39134	0.11540110	0.08772189	837.22092	1176.032144	154582.9330	16987.94544	2015-11	2020-10
savetheorangutan.sverige	4.91024555	5.521797	7.794242	6.155816	69.56139	36.24767	0.12097016	0.10233582	248.33785	274.263810	9449.8340	1203.01790	2015-11	2020-10
scouterna	4.03995560	4.455529	5.491676	4.471538	54.45172	31.63390	0.11357833	0.12777406	105.39734	233.443302	19195.2342	619.53388	2018-10	2020-10
sjoraddning	2.82205029	4.249396	5.263056	4.983462	62.12959	40.72982	0.08518263	0.08823815	471.63153	460.309716	66985.2050	5353.00175	2015-11	2020-10
skanestadsmission	2.77805907	4.332528	4.803376	5.016963	52.64051	47.95403	0.09673725	0.10717720	155.84388	168.283791	8341.2633	2364.78667	2015-11	2020-10
sosbarnbyar	3.06171548	5.343035	7.082636	5.936882	65.26569	42.73543	0.12368877	0.14766421	168.25732	314.139661	44470.2531	2237.20041	2015-11	2020-10
spadbarnsfonden	3.60000000	5.935990	7.831579	8.076555	72.41579	76.80685	0.10151621	0.08476173	96.58421	180.038240	7288.8211	163.55828	2020-01	2020-10
stadsmissionen	2.70429570	3.884903	4.040959	4.041203	45.03596	31.18161	0.09538449	0.10930400	227.83217	633.775181	24082.0749	5844.92506	2015-11	2020-10
stadsmissioniorebro	3.05872757	4.019537	3.672104	4.252852	36.24959	29.89116	0.10046460	0.11485921	65.71289	87.640303	3756.4127	461.88895	2016-01	2020-10
starforlifeofficial	4.85521886	6.534931	5.791246	7.635501	55.02694	53.62734	0.08817729	0.09642813	63.86869	63.154623	8765.2862	298.99172	2016-03	2020-10
suicidezero	0.93155894	6.177022	8.361217	8.653350	82.98099	67.19349	0.10009304	0.08898536	450.58175	549.820984	64008.1255	2312.05900	2019-02	2020-10
svenskafreds	1.26274510	5.560780	6.953725	7.606918	81.31451	62.53191	0.08184393	0.07125861	103.27529	165.300047	12021.3388	1364.47313	2015-11	2020-10
svenskalivraddningssallskapet	1.88931298	3.505140	2.927481	3.654601	38.81870	29.22425	0.08322500	0.15456969	85.96374	133.596152	32147.3053	304.69871	2015-11	2020-10
sverigeforunhcr	1.70671378	4.488184	5.528269	5.263700	51.38781	38.86544	0.11347227	0.09487778	384.04770	666.155247	65812.0839	11779.81456	2015-11	2020-10
sverigesstadsmissioner	1.01426307	4.004535	4.326466	4.601026	49.94453	37.25598	0.08469020	0.08479443	28.66878	27.206377	1620.1569	144.76425	2017-08	2020-10
thehungerprojectse	1.75510204	4.091800	4.710204	4.679700	50.86224	31.00381	0.09095990	0.08593772	20.20918	23.158646	4421.6551	1508.66905	2016-02	2020-10
ungcancer	2.20069505	6.536229	10.657689	8.523682	99.72719	66.47295	0.12140692	0.36030345	437.13467	940.105918	151239.6533	1160.85746	2015-11	2020-10
uppsalastadsmission	4.30509745	4.314774	5.715892	4.763997	61.70915	33.87443	0.09624216	0.07713668	82.82384	144.694566	3948.2106	1258.89102	2015-11	2020-10
vasterasstadsmission	3.25196850	5.257573	4.569554	6.210797	53.85433	59.55482	0.08233304	0.11936839	68.15617	230.660739	5568.7966	636.76250	2015-11	2020-10
viskogen	3.50000000	4.613743	5.703390	4.879541	66.30085	40.32114	0.08997433	0.08202574	806.32839	943.540559	53655.0106	9048.02054	2016-02	2020-10
warchildsverige	3.55962060	5.314259	7.670732	5.923642	58.73984	35.99985	0.15023352	0.14425350	29.37534	36.957217	3307.2846	1458.45862	2017-01	2020-10
wateraidswe	2.07035176	4.663428	5.819095	5.933352	64.95678	52.85492	0.09632118	0.09232208	78.00402	198.772065	7213.3397	2984.03191	2015-11	2020-10
weeffect	2.20571429	4.279764	5.158095	5.529221	58.09143	52.59640	0.08879443	0.07689710	240.18857	700.033519	64381.9886	6554.56075	2016-04	2020-10
worldschildrensprize	2.64444444	6.098896	8.000000	7.707959	68.17037	47.13534	0.12382472	0.10876342	792.30741	2102.117358	143251.1630	2073.82337	2017-06	2020-10

# Convert 'm7_first' and 'm7_last' to Date type
pd <- result_df %>%
  mutate(m7_first = as.Date(paste0(m7_first,"-01")),
         m7_last = as.Date(paste0(m7_last,"-01")))

# Reorder 'org' alphabetically and reverse the levels to put the first alphabetically at the top
pd$org <- factor(pd$org, levels = rev(sort(unique(pd$org))))

# Create a Gantt chart
ggplot(pd, aes(y = org, x = m7_first, xend = m7_last, yend = org)) +
  geom_segment(size = 6, color = "blue") +
  theme_minimal() +
  labs(title = "Gantt Chart of Organizations and Date Ranges", 
       x = "Date", y = "Organization") +
  theme(axis.text.y = element_text(size = rel(1.5)))  # Increased font size for y-axis labels

Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
ℹ Please use `linewidth` instead.

aggregate measures by org_type

# Aggregate the data
aggregated_data <- tmp %>%
  select(starts_with("m1_"), starts_with("m2_"), starts_with("m3_"),
         starts_with("m4_"), starts_with("m5_"), starts_with("m6_"),
         starts_with("m7_"), org_type) %>%
  group_by(org_type) %>%
  summarize(across(starts_with("m1_"):starts_with("m6_"),
                   list(mean = ~ mean(., na.rm = TRUE),
                        sd = ~ sd(., na.rm = TRUE))),
            m7_first = first(m7_date),
            m7_last = last(m7_date))

# View the aggregated data
result_df = aggregated_data |> as_tibble()
cat(simplermarkdown::md_table(result_df))

org_type	m1_sa_val_mean	m1_sa_val_sd	m2_sa_int_abs_mean	m2_sa_int_abs_sd	m3_wc_mean	m3_wc_sd	m4_sa_int_rel_mean	m4_sa_int_rel_sd	m5_e_index_mean	m5_e_index_sd	m6_follow_mean	m6_follow_sd	m7_first	m7_last
1	3.057028	4.200284	4.209101	4.490529	43.90755	34.39770	0.10279366	0.13813162	99.72494	278.0129	13957.86	10586.60	2015-11	2020-10
2	3.149388	4.646597	4.507676	5.347176	49.40038	45.09651	0.11354563	0.28007334	78.82198	489.3205	14093.29	29878.23	2015-11	2020-10
3	2.141953	5.016731	5.421183	6.198936	58.45656	51.56874	0.09634295	0.11085358	341.21398	1191.6792	56859.58	99903.65	2015-11	2020-10
4	2.735802	5.520697	6.159303	7.133257	65.51294	58.48337	0.09477381	0.13830018	262.78918	1303.0001	39396.08	69324.41	2015-11	2020-10
5	2.531806	4.904112	5.162154	5.479769	54.80868	44.49427	0.10019346	0.11842419	439.14325	804.8198	36520.46	29556.96	2015-11	2020-10
6	3.791966	5.656389	6.117647	6.759687	66.88881	50.70691	0.09322482	0.08810466	91.45875	223.4714	37878.40	45875.47	2015-11	2020-10
7	1.300783	4.782517	5.151828	6.407339	56.15904	51.50539	0.08997515	0.11165394	115.98863	307.6831	14570.76	22106.36	2015-11	2020-10
9	2.088196	4.971329	6.050024	5.928458	59.13269	44.89400	0.10593526	0.10541065	257.18140	963.9193	39475.60	63837.05	2015-11	2020-10

240118: boxplot measures

tmp <- dtp |> 
  select(c(19,22,27,14,23,25,11,6)) |>
  mutate(
    m1_sa_val=sa_val,
    m2_sa_int_abs=sa_int_abs,
    m3_wc=wc,
    m4_sa_int_rel=sa_int_abs / wc,
  ) |> 
  filter(
    e_index < 10000,
    m1_sa_val < 100,
    m2_sa_int_abs < 50,
    m3_wc < 500,
    m4_sa_int_rel < 5
  ) |>
  sample_n(size = 10000)

tmp |> as_tibble()

# A tibble: 10,000 × 12
   date  month org_t…¹ sa_val sa_in…²    wc e_index follow m1_sa…³ m2_sa…⁴ m3_wc
   <chr> <dbl>   <int>  <int>   <int> <int>   <int>  <int>   <int>   <int> <int>
 1 2015…     2       3      2       2    51      26   1138       2       2    51
 2 2017…    16       9     -7      11    94      41   3282      -7      11    94
 3 2020…    56       4      3       7    50     735  12410       3       7    50
 4 2018…    32       4    -10      20   187     162  88402     -10      20   187
 5 2020…    52       5      0       4    22      76  94053       0       4    22
 6 2019…    44       3     -1       3    57     302 124163      -1       3    57
 7 2017…    24       7      0       0    13     140   3263       0       0    13
 8 2020…    59       9     23      23   155      70  77600      23      23   155
 9 2017…    26       3      0       0     1      43    591       0       0     1
10 2018…    36       4      6       8    96      12  10527       6       8    96
# … with 9,990 more rows, 1 more variable: m4_sa_int_rel <dbl>, and abbreviated
#   variable names ¹​org_type, ²​sa_int_abs, ³​m1_sa_val, ⁴​m2_sa_int_abs

library(mgcv)

Loading required package: nlme

Attaching package: 'nlme'

The following object is masked from 'package:lme4':

    lmList

The following object is masked from 'package:dplyr':

    collapse

This is mgcv 1.9-0. For overview type 'help("mgcv-package")'.

# Create the plot
tmp |> pivot_longer(cols=c(9:12), names_to="measure", values_to="score") |>
  ggplot(aes(x=score, y=e_index)) +
  geom_point(size=0.5) + 
  geom_smooth(method="lm", se=FALSE, linewidth=1.0, color="blue") +
  # quadratic fit
  geom_smooth(method = "lm", formula = y ~ poly(x, 2), se = FALSE) + 
  # cubic fit
  geom_smooth(method = "lm", formula = y ~ poly(x, 3), se = FALSE) + 
  geom_smooth(method = "lm", formula = y ~ splines::bs(x, degree = 3), se = FALSE) + 
  geom_smooth(method="loess", se=FALSE, linewidth=1.0, color="red") +
  geom_smooth(method = "gam") + 
  facet_wrap(~measure, scales="free", nrow = 2, ncol = 2) +
  labs(
    title="Engagement by Sentiment",
    subtitle="Association Between Engagement and Sentiment",
    caption="",
    x="Sentiment",
    y="Engagement"
  ) +
  theme(
    legend.text = element_text(size = 10, face = "bold")
  )

`geom_smooth()` using formula = 'y ~ x'

`geom_smooth()` using formula = 'y ~ x'
`geom_smooth()` using formula = 'y ~ s(x, bs = "cs")'

240118: boxplot measures

org_type_labs=c(
"culture and recreation",
"education and research",
"health",
"social services ",
"environment",
"development and housing",
"law, advocacy an politics",
#"philantropic intermediaries and voluntarism promotion",
"international"
)

tmp = dtp |> as_tibble() |> 
select(c(19,22,27,14,23,25,11,6)) |>
mutate(sa_int_rel_wc=sa_int_abs/wc) |>
mutate(e_index_rel=e_index/follow) |>
mutate(e_index_rel=e_index) |>
#mutate(date=as.POSIXct(time, origin="1970-01-01", tz="UTC")) |>
mutate(date=as.Date(date)) |>
mutate(date=format(date, "%Y-%m")) |>
group_by(date, org_type) |>
summarize(
    m1_sa_val=mean(sa_val),
    m2_sa_int_abs=mean(sa_int_abs),
    m3_wc=mean(wc),
    m4_sa_int_rel_wc=mean(sa_int_rel_wc),
    #date=first(date),
    m5_e_index=mean(e_index_rel),
    m6_follow=mean(follow)
) 

`summarise()` has grouped output by 'date'. You can override using the
`.groups` argument.

# Custom labeller function with individual variable names
custom_labeller <- function(variable, value) {
  custom_labels <- c(
  m1_sa_val="sentiment valence", 
  m2_sa_int_abs="sentiment intensity",
  m3_wc="word count", 
  m4_sa_int_rel_wc="sentiment relative",
  m5_e_index="engagement index",
  m6_follow="follower count"
  )
  return(custom_labels[value])
}

tmp |> pivot_longer(cols=3:8, names_to="measure", values_to="score") |>
  ggplot(aes(x=measure, y=score, fill=as.factor(org_type))) +
  geom_boxplot() +
  scale_fill_manual(values=as.factor(tmp$org_type), labels=org_type_labs) + 
  facet_wrap(vars(measure), scales="free", labeller=as_labeller(custom_labeller)) +
  labs(
    title="measures descriptives",
    subtitle="sentiment measures and engagement",
    caption="",
    x="measure",
    y="score",
    fill="organization type"
  ) +
  theme(
    text=element_text(size=rel(5.0)),
    plot.title = element_text(size=rel(5.0), face="bold"),
    strip.text = element_text(size=rel(5.0)),
    #axis.text.x=element_text(angle=90, hjust=1),
    axis.text.x=element_blank(),  # Omit x-axis text
    axis.ticks.x=element_blank(), # Omit x-axis ticks
    legend.title = element_text(size=rel(5.0), face="bold"),
    legend.text = element_text(size=rel(5.0)),
  )

240118: measures over time, without org_type

tmp = dtp |> as_tibble() |> 
select(c(19,22,27,14,23,25,11,6)) |>
mutate(sa_int_rel_wc=sa_int_abs/wc) |>
mutate(e_index_rel=e_index/follow) |>
mutate(e_index_rel=e_index) |>
#mutate(date=as.POSIXct(time, origin="1970-01-01", tz="UTC")) |>
mutate(date=as.Date(date)) |>
mutate(date=format(date, "%Y-%m")) |>
#group_by(date, org_type) |>
group_by(date) |>
summarize(
    m1_sa_val=mean(sa_val),
    m2_sa_int_abs=mean(sa_int_abs),
    m3_wc=mean(wc),
    m4_sa_int_rel_wc=mean(sa_int_rel_wc),
    #date=first(date),
    m5_e_index=mean(e_index_rel),
    m6_follow=mean(follow)
) 

#tmp |> as_tibble()

# Custom labeller function with individual variable names
custom_labeller <- function(variable, value) {
  custom_labels <- c(
  m1_sa_val="sentiment valence", 
  m2_sa_int_abs="sentiment intensity",
  m3_wc="word count", 
  m4_sa_int_rel_wc="sentiment relative",
  m5_e_index="engagement index",
  m6_follow="follower count"
  )
  return(custom_labels[value])
}

tmp |> pivot_longer(cols=2:7, names_to="measure", values_to="score") |>
  ggplot(aes(x=as.Date(paste0(date,"-01")), y=score)) + #, group=org_type, color=as.factor(org_type))) +
  geom_point(size=1.5) + 
  geom_smooth(method=lm, formula = y ~ x, se=F, linewidth=1.5, color="blue") +
  #scale_x_date(date_breaks = "1 year", date_labels = "%Y") + 
  #scale_x_discrete(labels=ifelse(seq_along(tmp$date) %% 2 == 1, tmp$date, "")) +
  #scale_x_discrete(labels=ifelse((1:60 - 1) %% 4 == 0, as.character(1:60), "")) +
  #scale_x_discrete(labels=ifelse(seq_along(sort(unique(tmp$date))) %% 4 == 1, sort(unique(tmp$date)), "")) +
  #scale_color_manual(values=as.factor(tmp$org_type), labels=org_type_labs) + 
  facet_wrap(vars(measure), scales="free", labeller=as_labeller(custom_labeller)) +
  labs(
    title="measures by time",
    subtitle="sentiment measures and engagement",
    caption="sentiment is increasing over time, engagment is decreasing",
    x="date of post",
    y="score",
    #color="blue"
  ) +
  theme(
    text=element_text(size=rel(5.0)),
    plot.title=element_text(size=rel(5.0), face="bold"),
    strip.text=element_text(size=rel(5.0)),
    #axis.text.x=element_text(angle=0, hjust=1),
    #legend.position = "top",
    #legend.key.size = unit(1, "cm"),
    #legend.title = element_text(size=rel(5.0), face="bold"),
    #legend.text = element_text(size=rel(5.0)),
  )

240110: back to afinn

• översätta till årtal + månad (t.ex. 2015-01)
• valens, intensitet, wc, sent/wc, över tid

tmp = dtp |> as_tibble() |> 
select(c(19,22,27,14,23,25,11,6)) |>
mutate(sa_int_rel_wc=sa_int_abs/wc) |>
mutate(e_index_rel=e_index/follow) |>
mutate(e_index_rel=e_index) |>
#mutate(date=as.POSIXct(time, origin="1970-01-01", tz="UTC")) |>
mutate(date=as.Date(date)) |>
mutate(date=format(date, "%Y-%m")) |>
group_by(date, org_type) |>
summarize(
    m1_sa_val=mean(sa_val),
    m2_sa_int_abs=mean(sa_int_abs),
    m3_wc=mean(wc),
    m4_sa_int_rel_wc=mean(sa_int_rel_wc),
    #date=first(date),
    m5_e_index=mean(e_index_rel),
    m6_follow=mean(follow)
) 

`summarise()` has grouped output by 'date'. You can override using the
`.groups` argument.

# Custom labeller function with individual variable names
custom_labeller <- function(variable, value) {
  custom_labels <- c(
  m1_sa_val="sentiment valence", 
  m2_sa_int_abs="sentiment intensity",
  m3_wc="word count", 
  m4_sa_int_rel_wc="sentiment relative",
  m5_e_index="engagement index",
  m6_follow="follower count"
  )
  return(custom_labels[value])
}

tmp |> pivot_longer(cols=3:8, names_to="measure", values_to="score") |>
  #ggplot(aes(x=as.Date(paste0(date,"-01")), y=score, group=org_type, color=as.factor(org_type))) +
  ggplot(aes(x=date, y=score, group=org_type, color=as.factor(org_type))) +
  geom_point(size=1.5) + 
  geom_smooth(method=lm, formula=y~x, se=F, linewidth=1.5) +
  #scale_x_date(date_breaks = "1 year", date_labels = "%Y") + 
  #scale_x_discrete(labels=ifelse(seq_along(tmp$date) %% 2 == 1, tmp$date, "")) +
  #scale_x_discrete(labels=ifelse((1:60 - 1) %% 4 == 0, as.character(1:60), "")) +
  scale_x_discrete(labels=ifelse(seq_along(sort(unique(tmp$date))) %% 4 == 1, sort(unique(tmp$date)), "")) +
  scale_color_manual(values=as.factor(tmp$org_type), labels=org_type_labs) + 
  facet_wrap(vars(measure), scales="free", labeller=as_labeller(custom_labeller)) +
  labs(
    title="measures over time",
    subtitle="sentiment measures and engagement",
    caption="sentiment is increasing over time, engagment is decreasing",
    x="date of post",
    y="score",
    color="organization type"
  ) +
  theme(
    text=element_text(size=rel(5.0)),
    plot.title = element_text(size=rel(5.0), face="bold"),
    strip.text = element_text(size=rel(5.0)),
    axis.text.x=element_text(angle=90, hjust=1),
    #legend.position = "top",
    #legend.key.size = unit(1, "cm"),
    legend.title = element_text(size=rel(5.0), face="bold"),
    legend.text = element_text(size=rel(5.0)),
  )

• sentiment mått vs engagement index
• sentiment extremer + exempel poster

tmp = dtp |> 
select(c(19,22,27,14,23,25,11,6)) |>
mutate(sa_int_rel_wc=sa_int_abs/wc) |>
mutate(e_index_rel=e_index/follow) |>
mutate(e_index_rel=e_index) |>
group_by(month) |>
summarize(
    m1_sa_val=mean(sa_val),
    m2_sa_int_abs=mean(sa_int_abs),
    m3_wc=mean(wc),
    m4_sa_int_rel_wc=mean(sa_int_rel_wc),
    #date=first(date)
    m0_e_index=mean(e_index_rel)
)

tmp |> pivot_longer(cols=2:5, names_to="measure", values_to="score") |>
  ggplot(aes(x=score, y=m0_e_index)) +
  geom_point(size=1.5) + 
  geom_smooth(method=lm, linewidth=1.5, se=F) +
  facet_wrap(~measure, scales="free", nrow = 2, ncol = 2) +
  labs(
    title="engagement by sentiment",
    subtitle="association between engagement and sentiment",
    caption="flat or negative trends",
    x="sentiment",
    y="engagement",
    #color="organization type"
  ) +
  theme(
    #legend.position = "top",  # Reposition legend to top
    #legend.key.size = unit(1, "cm"),  # Change size of legend keys
    legend.text = element_text(size = 10, face = "bold")  # Change legend text appearance
  )

`geom_smooth()` using formula = 'y ~ x'

if (T) {
knitr::knit_exit()
#exit()
#q()
#stop("here..")
}